{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03772161448509996,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003772161448509996,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0003772161448509996,
      "eval_loss": NaN,
      "eval_runtime": 227.9219,
      "eval_samples_per_second": 9.797,
      "eval_steps_per_second": 1.228,
      "step": 1
    },
    {
      "epoch": 0.0007544322897019992,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.001131648434552999,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0015088645794039985,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.001886080724254998,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.002263296869105998,
      "grad_norm": NaN,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002640513013956997,
      "grad_norm": NaN,
      "learning_rate": 1.4e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.003017729158807997,
      "grad_norm": NaN,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0033949453036589967,
      "grad_norm": NaN,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0033949453036589967,
      "eval_loss": NaN,
      "eval_runtime": 227.0397,
      "eval_samples_per_second": 9.835,
      "eval_steps_per_second": 1.233,
      "step": 9
    },
    {
      "epoch": 0.003772161448509996,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.004149377593360996,
      "grad_norm": NaN,
      "learning_rate": 1.999390827019096e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.004526593738211996,
      "grad_norm": NaN,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.004903809883062995,
      "grad_norm": NaN,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.005281026027913994,
      "grad_norm": NaN,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.005658242172764994,
      "grad_norm": NaN,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.006035458317615994,
      "grad_norm": NaN,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.006412674462466994,
      "grad_norm": NaN,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0067898906073179935,
      "grad_norm": NaN,
      "learning_rate": 1.961261695938319e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0067898906073179935,
      "eval_loss": NaN,
      "eval_runtime": 226.9822,
      "eval_samples_per_second": 9.838,
      "eval_steps_per_second": 1.234,
      "step": 18
    },
    {
      "epoch": 0.007167106752168993,
      "grad_norm": NaN,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.007544322897019992,
      "grad_norm": NaN,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.007921539041870993,
      "grad_norm": NaN,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.008298755186721992,
      "grad_norm": NaN,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.00867597133157299,
      "grad_norm": NaN,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.009053187476423991,
      "grad_norm": NaN,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.00943040362127499,
      "grad_norm": NaN,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.00980761976612599,
      "grad_norm": NaN,
      "learning_rate": 1.848048096156426e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.01018483591097699,
      "grad_norm": NaN,
      "learning_rate": 1.8290375725550417e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.01018483591097699,
      "eval_loss": NaN,
      "eval_runtime": 227.0173,
      "eval_samples_per_second": 9.836,
      "eval_steps_per_second": 1.233,
      "step": 27
    },
    {
      "epoch": 0.010562052055827989,
      "grad_norm": NaN,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.01093926820067899,
      "grad_norm": NaN,
      "learning_rate": 1.788010753606722e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.011316484345529988,
      "grad_norm": NaN,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.011693700490380989,
      "grad_norm": NaN,
      "learning_rate": 1.7431448254773943e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.012070916635231988,
      "grad_norm": NaN,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.012448132780082987,
      "grad_norm": NaN,
      "learning_rate": 1.6946583704589973e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.012825348924933987,
      "grad_norm": NaN,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.013202565069784986,
      "grad_norm": NaN,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.013579781214635987,
      "grad_norm": NaN,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.013579781214635987,
      "eval_loss": NaN,
      "eval_runtime": 226.9903,
      "eval_samples_per_second": 9.837,
      "eval_steps_per_second": 1.234,
      "step": 36
    },
    {
      "epoch": 0.013956997359486986,
      "grad_norm": NaN,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.014334213504337986,
      "grad_norm": NaN,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.014711429649188985,
      "grad_norm": NaN,
      "learning_rate": 1.529919264233205e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.015088645794039984,
      "grad_norm": NaN,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.015465861938890985,
      "grad_norm": NaN,
      "learning_rate": 1.469471562785891e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.015843078083741986,
      "grad_norm": NaN,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.016220294228592985,
      "grad_norm": NaN,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.016597510373443983,
      "grad_norm": NaN,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.016974726518294982,
      "grad_norm": NaN,
      "learning_rate": 1.342020143325669e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.016974726518294982,
      "eval_loss": NaN,
      "eval_runtime": 227.0243,
      "eval_samples_per_second": 9.836,
      "eval_steps_per_second": 1.233,
      "step": 45
    },
    {
      "epoch": 0.01735194266314598,
      "grad_norm": NaN,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.017729158807996984,
      "grad_norm": NaN,
      "learning_rate": 1.2756373558169992e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.018106374952847983,
      "grad_norm": NaN,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.01848359109769898,
      "grad_norm": NaN,
      "learning_rate": 1.2079116908177592e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.01886080724254998,
      "grad_norm": NaN,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.01923802338740098,
      "grad_norm": NaN,
      "learning_rate": 1.1391731009600655e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.01961523953225198,
      "grad_norm": NaN,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.01999245567710298,
      "grad_norm": NaN,
      "learning_rate": 1.0697564737441254e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.02036967182195398,
      "grad_norm": NaN,
      "learning_rate": 1.0348994967025012e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.02036967182195398,
      "eval_loss": NaN,
      "eval_runtime": 227.0255,
      "eval_samples_per_second": 9.836,
      "eval_steps_per_second": 1.233,
      "step": 54
    },
    {
      "epoch": 0.02074688796680498,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.021124104111655977,
      "grad_norm": NaN,
      "learning_rate": 9.651005032974994e-06,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.02150132025650698,
      "grad_norm": NaN,
      "learning_rate": 9.302435262558748e-06,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.02187853640135798,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-06,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.022255752546208978,
      "grad_norm": NaN,
      "learning_rate": 8.60826899039935e-06,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.022632968691059976,
      "grad_norm": NaN,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.023010184835910975,
      "grad_norm": NaN,
      "learning_rate": 7.92088309182241e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.023387400980761978,
      "grad_norm": NaN,
      "learning_rate": 7.580781044003324e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.023764617125612977,
      "grad_norm": NaN,
      "learning_rate": 7.243626441830009e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.023764617125612977,
      "eval_loss": NaN,
      "eval_runtime": 227.0274,
      "eval_samples_per_second": 9.836,
      "eval_steps_per_second": 1.233,
      "step": 63
    },
    {
      "epoch": 0.024141833270463976,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.024519049415314974,
      "grad_norm": NaN,
      "learning_rate": 6.579798566743314e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.024896265560165973,
      "grad_norm": NaN,
      "learning_rate": 6.25393406584088e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.025273481705016976,
      "grad_norm": NaN,
      "learning_rate": 5.932633569242e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.025650697849867975,
      "grad_norm": NaN,
      "learning_rate": 5.616288532109225e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.026027913994718974,
      "grad_norm": NaN,
      "learning_rate": 5.305284372141095e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.026405130139569973,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.026782346284420975,
      "grad_norm": NaN,
      "learning_rate": 4.700807357667953e-06,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.027159562429271974,
      "grad_norm": NaN,
      "learning_rate": 4.408070965292534e-06,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.027159562429271974,
      "eval_loss": NaN,
      "eval_runtime": 226.9394,
      "eval_samples_per_second": 9.84,
      "eval_steps_per_second": 1.234,
      "step": 72
    },
    {
      "epoch": 0.027536778574122973,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-06,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.02791399471897397,
      "grad_norm": NaN,
      "learning_rate": 3.8433852467434175e-06,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.02829121086382497,
      "grad_norm": NaN,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.028668427008675973,
      "grad_norm": NaN,
      "learning_rate": 3.308693936411421e-06,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.029045643153526972,
      "grad_norm": NaN,
      "learning_rate": 3.0534162954100264e-06,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.02942285929837797,
      "grad_norm": NaN,
      "learning_rate": 2.8066019966134907e-06,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.02980007544322897,
      "grad_norm": NaN,
      "learning_rate": 2.5685517452260566e-06,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.03017729158807997,
      "grad_norm": NaN,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.03055450773293097,
      "grad_norm": NaN,
      "learning_rate": 2.119892463932781e-06,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.03055450773293097,
      "eval_loss": NaN,
      "eval_runtime": 226.916,
      "eval_samples_per_second": 9.841,
      "eval_steps_per_second": 1.234,
      "step": 81
    },
    {
      "epoch": 0.03093172387778197,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.031308940022632965,
      "grad_norm": NaN,
      "learning_rate": 1.709624274449584e-06,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.03168615616748397,
      "grad_norm": NaN,
      "learning_rate": 1.5195190384357405e-06,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.03206337231233497,
      "grad_norm": NaN,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.03244058845718597,
      "grad_norm": NaN,
      "learning_rate": 1.1705240714107301e-06,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.03281780460203697,
      "grad_norm": NaN,
      "learning_rate": 1.012059537008332e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.03319502074688797,
      "grad_norm": NaN,
      "learning_rate": 8.645454235739903e-07,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.033572236891738966,
      "grad_norm": NaN,
      "learning_rate": 7.281614543321269e-07,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.033949453036589965,
      "grad_norm": NaN,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.033949453036589965,
      "eval_loss": NaN,
      "eval_runtime": 226.9288,
      "eval_samples_per_second": 9.84,
      "eval_steps_per_second": 1.234,
      "step": 90
    },
    {
      "epoch": 0.034326669181440964,
      "grad_norm": NaN,
      "learning_rate": 4.894348370484648e-07,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.03470388532629196,
      "grad_norm": NaN,
      "learning_rate": 3.8738304061681107e-07,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.03508110147114297,
      "grad_norm": NaN,
      "learning_rate": 2.970427372400353e-07,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.03545831761599397,
      "grad_norm": NaN,
      "learning_rate": 2.1852399266194312e-07,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.035835533760844966,
      "grad_norm": NaN,
      "learning_rate": 1.519224698779198e-07,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.036212749905695965,
      "grad_norm": NaN,
      "learning_rate": 9.731931258429638e-08,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.036589966050546964,
      "grad_norm": NaN,
      "learning_rate": 5.4781046317267103e-08,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.03696718219539796,
      "grad_norm": NaN,
      "learning_rate": 2.4359497401758026e-08,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.03734439834024896,
      "grad_norm": NaN,
      "learning_rate": 6.091729809042379e-09,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.03734439834024896,
      "eval_loss": NaN,
      "eval_runtime": 226.9627,
      "eval_samples_per_second": 9.839,
      "eval_steps_per_second": 1.234,
      "step": 99
    },
    {
      "epoch": 0.03772161448509996,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.66533937241129e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}